Developer Tooling

MCP server for Gitcode platform - Issue and Pull Request operations

MCP server for Microsoft PowerPlatform/Dataverse - read-only access (production-safe)

Vercel connector for antidrift — deployments, projects, domains, environment variables

Modern Nuxt 4 documentation theme with auto-generated component docs, AI chat assistant, MCP server, and complete developer experience optimization.

MCP server for Statuser.cloud — monitor servers, manage incidents and status pages from your AI client

Configurable tool bundle for AI coding agents — use via MCP server, CLI, or agent skills. npm wrapper for the Rust binary.

Local-first analytics for AI agent skills. Track usage, measure context budget, and prune what you don't use.

MCP server for Freshservice – manage tickets, agents and conversations from any MCP-compatible AI client

Server security audit (413 checks), hardening, and fleet management across 4 cloud providers.

Modern SSH for AI agents — cloud servers to BusyBox routers, with destructive commands blocked.

Spec-driven dev workflow MCP: start_* orchestration, memory, GitNexus, quality gates.

MCP server bridging OpenGrok search engine with AI for instant context across massive codebases.

Async context compaction for the Pi coding agent: precompute background summaries for long sessions.

Observability MCP server: query LLM cost/errors/latency & operate alerts/evals from Claude/Cursor

Records your screen and voice, returns one annotated screenshot and finding per mark.

Cited, OSV-gated, injection-hardened web briefs for coding agents. Verified, never raw web.

Unofficial local-first ClickBus MCP for place search, trip prices and booking history. Never pays unless CLICKBUS_ALLOW_MUTATIONS and explicit_user_intent are both set.

Give AI agents persistent context in n8n. Turn docs, code repositories, PDFs, specs, and other MCP servers into a live Model Context Protocol endpoint your workflows and agents read before they act, without writing code.

Persistent memory for AI agents, governed by the human and stored on their own machine.

Compile one source of coding rules to CLAUDE.md, AGENTS.md, .cursor/rules and copilot-instructions — then run tasks through an agent under gates.